For Educators & students
Shape model behavior.
Your students already use AI. Understand how its answers get made — where they come from, how much they vary, and how they're judged — by changing one thing at a time and watching what moves.
You already know how to check an answer.
Source-checking, rubric grading, and knowing one essay isn't the whole student — the habits of good teaching are the habits of understanding a model.
A suggested path.
- 01LessonPrompts as designA prompt is a variable you can change and test — not a magic spell.
- 02PlaygroundDiff modeRun one prompt through two configurations side-by-side. The fastest way to feel how prompts shape outputs.
- 03LessonContext is the interfaceYour system prompt is a fraction of what the model reads. The rest arrives at runtime, from systems nobody designed.
- 04PlaygroundContext labOne question, several context sets. Your system prompt is a fraction of what the model reads — see the rest, and where the answer came from.
- 05LessonEvaluationRubrics + sample sets. Make “good” measurable — then find out what your rubric actually rewards.
- 06PlaygroundEval labRubric-based evaluation. Define what good looks like, score the model against it, watch the average move.
- 07ExperimentDoes a longer answer get a better grade?An AI grader scores the same student answer with and without filler that adds nothing.